© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35909
    Prev
    Next
    INDEX
    Explanations

    descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on strong sentiment-bearing modifiers—particularly vivid adjectives and adverbs that intensify a description.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considered
    -1.08
     devenus
    -1.07
     shown
    -1.00
     considerada
    -0.97
     leggi
    -0.96
     остав
    -0.96
    تیاز
    -0.93
     fournies
    -0.90
     deemed
    -0.90
     を
    -0.89
    POSITIVE LOGITS
    撻
    1.04
     coinc
    0.98
     at
    0.97
     armados
    0.96
    Mvh
    0.96
    træ
    0.95
    whence
    0.93
    óp
    0.92
     or
    0.91
     cucharadas
    0.91
    Activations Density 0.035%

    No Known Activations